© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 8830
    Prev
    Next
    INDEX
    Explanations

    the indefinite articles "a" and "an" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uchs
    -0.15
    rig
    -0.15
    tega
    -0.15
    ãĥ¬ãĤ¹
    -0.14
    ective
    -0.14
    _possible
    -0.14
    vern
    -0.14
    alet
    -0.13
    lian
    -0.13
    ioxide
    -0.13
    POSITIVE LOGITS
     considerable
    0.50
     significant
    0.50
     substantial
    0.47
     large
    0.41
     greater
    0.40
    significant
    0.39
     Significant
    0.39
     знаÑĩ
    0.37
     sizable
    0.36
    large
    0.35
    Activations Density 0.030%

    No Known Activations